Summarization for Generative Relation Extraction in the Microbiome Domain
Journal:
arXiv
Published Date:
Jun 10, 2025
Abstract
We explore a generative relation extraction (RE) pipeline tailored to the
study of interactions in the intestinal microbiome, a complex and low-resource
biomedical domain. Our method leverages summarization with large language
models (LLMs) to refine context before extracting relations via
instruction-tuned generation. Preliminary results on a dedicated corpus show
that summarization improves generative RE performance by reducing noise and
guiding the model. However, BERT-based RE approaches still outperform
generative models. This ongoing work demonstrates the potential of generative
methods to support the study of specialized domains in low-resources setting.
